首頁資訊基于實(shí)車數(shù)據(jù)和BP

基于實(shí)車數(shù)據(jù)和BP

來源：泰然健康網(wǎng) 時(shí)間：2024年12月16日 06:20

基于實(shí)車數(shù)據(jù)和BP-AdaBoost算法的電動(dòng)汽車動(dòng)力電池健康狀態(tài)估計(jì)

基金項(xiàng)目:

國(guó)家自然科學(xué)(51465100)；廣西自然科學(xué)(2018GXNSFAA281282)；廣西自動(dòng)檢測(cè)技術(shù)與儀器重點(diǎn)實(shí)驗(yàn)室主任(YQ17110)；桂林電子科技大學(xué)研究生教育創(chuàng)新計(jì)劃資助項(xiàng)目(2021YCXS120)

Electric vehicle power battery SOH estimation based on real vehicle data and BP-Adaboost algorithm

摘要 | | 訪問統(tǒng)計(jì) | | | || 文章評(píng)論

摘要:

動(dòng)力電池健康狀態(tài)(State of Health, SOH)估計(jì)是電動(dòng)汽車領(lǐng)域關(guān)注的一個(gè)熱點(diǎn)，目前的大部分方法都是基于實(shí)驗(yàn)室測(cè)試數(shù)據(jù)進(jìn)行估計(jì)，忽略了實(shí)際車輛運(yùn)行情況。本文使用國(guó)家大數(shù)據(jù)聯(lián)盟平臺(tái)采集的實(shí)際車輛運(yùn)行數(shù)據(jù)進(jìn)行電池SOH的估計(jì)。數(shù)據(jù)預(yù)處理方面，在清洗異常數(shù)據(jù)時(shí)，保留了實(shí)車數(shù)據(jù)中合理的強(qiáng)噪聲數(shù)據(jù)，保證了數(shù)據(jù)的真實(shí)性。特征選擇方面，選擇容量增量曲線峰值和對(duì)應(yīng)的電壓以及基于安時(shí)積分得到的小片段充電容量數(shù)據(jù)。算法方面，針對(duì)真實(shí)數(shù)據(jù)的弱時(shí)序性問題，利用BP-Adaboost算法進(jìn)行電池SOH估計(jì)的研究。最后，利用同一類型三輛車的數(shù)據(jù)進(jìn)行了模型訓(xùn)練、測(cè)試和驗(yàn)證，預(yù)測(cè)結(jié)果與LSTM-RNN算法對(duì)比，BP-Adaboost算法估計(jì)誤差更小，平均絕對(duì)誤差MAE達(dá)到0.96%，因此，本文提出的方法可以應(yīng)用于實(shí)車電池SOH的高精度估計(jì)。

Abstract:

State of Health (SOH) estimation is a hot topic in the field of electric vehicles. Most of the current methods are based on test data in the laboratory, so the actual vehicle operations are ignored. In this paper, the real vehicle operation data from the National Big Data Alliance platform was used to estimate SOH. In terms of data preprocessing, reasonable strong noise data in real vehicle data are retained to ensure the authenticity of data when rinsing abnormal data. In terms of feature selection, the peak value of capacity increment curve and corresponding voltage are selected as well as the small segment charging capacity data obtained based on ampere-hour integration. In terms of algorithm, BP-Adaboost algorithm is used to estimate SOH of battery for the weak timing of real data. Finally, the model is trained, tested and verified by using the data of three vehicles of the same type. Compared with LSTM-RNN algorithm, the estimation error of BP-Adaboost algorithm is smaller, and MAE can reach 0.96%. Therefore, the proposed method can be applied to high-precision SOH estimation of real vehicle batteries.

引用本文

周仁,張向文. 基于實(shí)車數(shù)據(jù)和BP-AdaBoost算法的電動(dòng)汽車動(dòng)力電池健康狀態(tài)估計(jì)[J]. 科學(xué)技術(shù)與工程, 2022, 22(21): 9398-9406.
Zhou Ren, Zhang Xiangwen. Electric vehicle power battery SOH estimation based on real vehicle data and BP-Adaboost algorithm[J]. Science Technology and Engineering,2022,22(21):9398-9406.

復(fù)制

分享文章指標(biāo) 點(diǎn)擊次數(shù):231 下載次數(shù): 929 HTML閱讀次數(shù): 0 歷史收稿日期:2021-12-28 最后修改日期:2022-02-20 錄用日期:2022-02-24 在線發(fā)布日期: 2022-08-09